CN103617420A - Commodity fast recognition method and system based on image feature matching - Google Patents
Commodity fast recognition method and system based on image feature matching Download PDFInfo
- Publication number
- CN103617420A CN103617420A CN201310637710.0A CN201310637710A CN103617420A CN 103617420 A CN103617420 A CN 103617420A CN 201310637710 A CN201310637710 A CN 201310637710A CN 103617420 A CN103617420 A CN 103617420A
- Authority
- CN
- China
- Prior art keywords
- commodity
- image
- color
- feature
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a commodity fast recognition method and system based on image feature matching. The method comprises the following steps that photographing and segmentation are conducted on to-be-recognized commodities placed on a commodity delivery channel through a photographing device; extraction of color and shape low-level features is conducted on obtained commodity image, the color and shape low-level features of the current to-be-recognized commodities are searched for and roughly matched in a database after being coded, and therefore commodities in the database can be reduced; by means of local invariance features, commodities remaining in a commodity information base after reducing is conducted are accurately matched and recognized, and bills are generated. By means of the commodity fast recognition method and system, the commodity image appearances can be recognized conveniently, fast and accurately, and the bills are generated conveniently to close deals.
Description
Technical field
The present invention relates to a kind of commodity method for quickly identifying and system, particularly relate to a kind of commodity method for quickly identifying and system based on Image Feature Matching.
Background technology
Nowadays supermarket has become shopping that domestic and international consumer often patronizes and the main place of experience, but the automatic checkout system that supermarket mainly adopts is at present bar code scanning technology, there is problems such as handing over money queuing time length, to consumer, bring temporal waste and psychological dislike, Ye Gei businessman has brought loss economically simultaneously.How can improve gathering speed, to solve the supermarket shopping queuing phenomena of paying dues, be the emphasis that service quality is improved in current supermarket, is also that consumers in general thirst for the problem solving most.In view of this, the automatic retail checkout system of various convenience occurs in succession, as the FastLaneTM self-checkout system of main flow, RFID checkout lanes.Yet these checkout systems, when bringing convenience shopping to consumer, also exist various realistic problems, are restricting being widely used of they.
FastLaneTM self-checkout system, utilization be bar code scanning technology, bar code itself has some shortcomings, if label is scratched, pollutes or comes off, scanner is beyond recognition target etc.This product will lean on consumer oneself to scan transaction simultaneously, according to interview investigation, shows that consumer feels complex operation, is more ready to take traditional checkout mode.
RFID checkout lanes, utilize radio-frequency technique, there is conveniently advantage, but every commodity all want attaching rfid electronic tag can improve workload and the cost in supermarket self, from the interference of metal, liquid, human body, rush barrier problem in addition, wherein maximum shortcoming is exactly the with high costs of RFID tag.
In recent years, the recognizer based on accelerating robust features (Speeded Up Robust Features, SURF), processes and stronger robustness because it facilitates computing machine, obtains applying more and more widely.Yet in the face of huge commodity amount, the speed that SURF algorithm improves can not requirement of real time; And SURF can only process gray level image, and colouring information is had to inadequate natural endowment.
Summary of the invention
The deficiency existing for overcoming above-mentioned prior art, the present invention's object is to provide a kind of commodity method for quickly identifying and system based on Image Feature Matching, to realize, commodity picture appearance is carried out to convenient, quick, accurately identification, and generate bill and conveniently complete transaction.
For reaching above-mentioned and other object, the present invention proposes a kind of commodity method for quickly identifying based on Image Feature Matching, comprises the steps:
Step 1, utilizes filming apparatus that the commodity to be identified that are positioned on commodity Transfer pipe are taken pictures, cut apart;
Step 2, carries out the extraction of color, shape low-level feature to the commodity image obtaining, and after the color of current commodity to be identified, shape low-level feature are encoded, retrieves and slightly mate, to arrange the commodity that subtract in database in database;
Step 3, utilizes local invariant feature to subtract surplus commodities to row in commodity information database and carries out accurately coupling identification, generates bill.
Further, in step 1, utilize infrared facility to detect after commodity, trigger this filming apparatus, by this filming apparatus, these commodity to be identified are taken pictures, and store in the middle of internal memory.
Further, in step 2, color characteristic extraction and the coding of commodity image are comprised the steps:
By image from RGB color space conversion to hsv color space.
Calculate respectively red, orange, yellow, green, cyan, blue, purple, black, white, ten kinds of colors of ash shared color ratio in image.
Setting threshold, quantizes ten kinds of color ratios;
Rear ten kinds of main colors of quantification are divided into some parts, carry out respectively binary coding, and according to coding rule, be commodity distribute digital label, create commodity color coding tables of data.
Further, rear ten kinds of main colors of quantification are divided into 3,3,3,1 four parts, carry out respectively binary coding, are packed data length simultaneously, and to each several part, summation obtains the coded data of four, according to this coding rule, be commodity distribute digital label, create commodity color coding tables of data.
Further, in step 2, the Shape Feature Extraction of commodity image and coding are comprised the steps:
When the border of object is known, the basic configuration of portraying commodity by the size of its boundary rectangle;
To arbitrarily towards object, first determine the main shaft of object, then calculate length on the major axes orientation of reflection shape feature and the width in perpendicular direction;
Adopt the shape facility that is compared to of horizontal width and vertical width;
Step-up error, by mean value plus-minus 0.3 data that obtain of commodity image length breadth ratio in early stage, coupling take 0.8 as equally spaced data area, and take its region number as its coding, creates commodity coded shape data table.
Further, in step 3, be matched to power the highest and be greater than 90% both, think successfully to mate, thereby the merchandise news of obtaining, according to the merchandise news obtaining, generates bill.
Further, in step 3, by feature point detection, unique point description and Feature Points Matching, extract this local invariant feature.
Further, in step 2, by server to the color of current commodity to be identified, shape facility according to binary coding after, in database, retrieve and slightly mate.
For achieving the above object, the present invention also provides a kind of commodity system for rapidly identifying based on Image Feature Matching, at least comprises:
Image pickup module, utilizes filming apparatus to take the commodity to be identified that are positioned on commodity Transfer pipe;
Characteristic extracting module, carries out the extraction of color, shape low-level feature to the image of current shooting, and the color, the shape facility that extract are encoded, and obtains color coding data and coded shape data;
The thick matching module of feature is retrieved these color coding data and this coded shape data and slightly mates in database, and row subtracts the commodity in database;
SUFT exact matching module, utilizes local invariant feature to subtract surplus commodities to row in database and carries out accurately coupling identification, generates bill.
Further, this characteristic extracting module utilizes the processing and control module of this filming apparatus to carry out color and Shape Feature Extraction to present image, and by server, it is carried out to binary coding, forms color coding data and coded shape data.
Compared with prior art, a kind of commodity method for quickly identifying based on Image Feature Matching of the present invention and system are by utilizing filming apparatus to take pictures to the commodity to be identified of placing vertically or lying on commodity Transfer pipe, cut apart, extract the color of commodity image, shape low-level feature slightly mates as commodity image, from huge commodity storehouse, screen and remove a large amount of uncorrelated commodity, then utilize surf local invariant feature, carry out exact matching with the commodity characteristics of image in commodity information database after thick coupling, thereby realize commodity identification fast automatically, simultaneously, the present invention carries out numerical coding classification by the CF feature of every kind of commodity, make commodity to be identified directly to the commodity in commodity storehouse, carry out fast search, raising arithmetic speed that can be very large significantly row subtract the commodity amount in commodity storehouse, the commodity storehouse being beneficial to after later use efficient identification algorithm subtracts row is quick and precisely identified.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of a kind of commodity method for quickly identifying based on Image Feature Matching of the present invention;
Fig. 2 is the process flow diagram of the preferred embodiment of a kind of commodity method for quickly identifying based on Image Feature Matching of the present invention;
Fig. 3 is the system architecture diagram of a kind of commodity system for rapidly identifying based on Image Feature Matching of the present invention.
Embodiment
Below, by specific instantiation accompanying drawings embodiments of the present invention, those skilled in the art can understand other advantage of the present invention and effect easily by content disclosed in the present specification.The present invention also can be implemented or be applied by other different instantiation, and the every details in this instructions also can be based on different viewpoints and application, carries out various modifications and change not deviating under spirit of the present invention.
Fig. 1 is the flow chart of steps of a kind of commodity method for quickly identifying based on Image Feature Matching of the present invention.As shown in Figure 1, a kind of commodity method for quickly identifying based on Image Feature Matching of the present invention, comprises the steps:
SURF feature is a kind of local feature of image, when target image rotates, yardstick convergent-divergent, brightness be when change, has unchangeability, and visual angle change, affined transformation and noise etc. are also had to stability to a certain degree.
In the present invention, SURF feature extraction comprises following process: feature point detection, unique point are described and Feature Points Matching three parts.In preferred embodiment of the present invention, feature point detection has adopted the Hai Sai based on Hessian() detecting device of matrix, its stability and repeatable aspect be all better than the detecting device based on Harris.
In step 102, the color characteristic extraction of commodity image and the step of coding are comprised the steps:
Step 1, by image from RGB color space conversion to hsv color space.
Step 2, calculates respectively red, orange, yellow, green, cyan, blue, purple, black, white, ten kinds of colors of ash shared color ratio in image.
Step 3, setting threshold, quantizes ten kinds of color ratios.For example being greater than threshold value is 1, otherwise is 0.
Step 4, is divided into 3,3 by rear ten kinds of main colors of quantification, and 3,1 four parts, carry out respectively binary coding.For packed data length, to each several part, summation obtains the coded data of four.According to this coding rule, be commodity distribute digital label, create commodity color coding tables of data.
In step 102, the step of the Shape Feature Extraction of commodity image and coding is comprised the steps:
(1) when the border of object is known, the basic configuration of portraying commodity by the size of its boundary rectangle.Utilize the boundary rectangle of commodity on change in coordinate axis direction, obtain horizontal span and the vertical span of object.
(2) to arbitrarily towards object, first determine the main shaft of object, then calculate length on the major axes orientation of reflection shape feature and the width in perpendicular direction.
(3) when image size changes, require shape facility to there is unchangeability.Therefore adopt the shape facility that is compared to of horizontal width and vertical width.
(4) step-up error, by mean value plus-minus 0.3 data that obtain of commodity image length breadth ratio in early stage, coupling take 0.8 as equally spaced data area (as table 1), and take its region number as its coding, creates commodity coded shape data table.
Table 1
Ratio is divided | (0,0.8] | (0.8,1.6] | (1.6,2.4] | (2.4,3.2] | (3.2,4.0] | (4.0,4.8] | … |
Coded data | 1 | 2 | 3 | 4 | 5 | 6 | … |
Fig. 2 is the process flow diagram of the preferred embodiment of a kind of commodity method for quickly identifying based on Image Feature Matching of the present invention.In preferred embodiment of the present invention, the present invention's the commodity method for quickly identifying based on Image Feature Matching comprises the steps:
Step 1, image capture, is detected after commodity by infrared facility, triggers camera, utilizes camera to take pictures to the commodity of placing vertically or lying on Transfer pipe, and the current shooting image collecting is stored in internal memory.
Step 2, image is cut apart.Utilizing the processing and control module of camera to carry out feature extraction to present image, is mainly to color and Shape Feature Extraction, and by server, it is carried out to binary coding, forms color coding data and coded shape data.
Step 3 is retrieved color coding data and coded shape data and slightly mates in database.Specifically, first color coding data retrieved in database and slightly mated, dwindling coupling commodity amount, and then coded shape data retrieved in database and slightly mated, further dwindling coupling commodity amount.
Step 4, SUFT coupling.Utilize SUFT feature (local invariant feature) to carry out exact matching.Be matched to power the highest and be greater than 90% both, think successfully to mate, thereby the merchandise news of obtaining, cashier on POS terminating machine according to the merchandise news obtaining, obtain trade name and price, generate bill and complete whole transaction, if coupling is made mistakes, system alarm, helps through operation by attendant.
Fig. 3 is the system architecture diagram of a kind of commodity system for rapidly identifying based on Image Feature Matching of the present invention.As shown in Figure 3, a kind of commodity system for rapidly identifying based on Image Feature Matching of the present invention, at least comprises: image pickup module 301, characteristic extracting module 302, the thick matching module 303 of feature, SUFT exact matching module 304.
Wherein, image pickup module 301 utilizes filming apparatus to take the commodity to be identified that are positioned on commodity Transfer pipe, and the current shooting image collecting is stored in internal memory; The image of 302 pairs of current shooting of characteristic extracting module carries out the extraction of color, shape facility, and the color, the shape facility that extract are encoded, and obtains color coding data and coded shape data; The thick matching module 303 of feature is retrieved color coding data and coded shape data and slightly mates in database, and a large amount of rows subtract the commodity in commodity information database; SUFT exact matching module 304 is utilized local invariant feature surf to subtract surplus commodities to row in commodity information database to carry out accurately coupling identification, generate bill.
Specifically, image pickup module 301 utilizes camera to take pictures to the commodity of placing vertically or lying on Transfer pipe, and the current shooting image collecting is stored in internal memory; Characteristic extracting module 302 utilizes the processing and control module of camera to carry out feature extraction to present image, is mainly to color and Shape Feature Extraction, and by server, it is carried out to binary coding, forms color coding data and coded shape data; The thick matching module 303 of feature is first retrieved color coding data and is slightly mated in database, dwindles coupling commodity amount, and then coded shape data is retrieved in database and slightly mated, and further dwindles coupling commodity amount; SUFT exact matching module 304 utilizes SUFT feature (local invariant feature) to carry out exact matching, be matched to power the highest and be greater than 90% both, think successfully to mate, thereby the merchandise news of obtaining, cashier according to the merchandise news obtaining, obtains trade name and price on POS terminating machine, generate bill and complete whole transaction, if coupling is made mistakes, system alarm, helps through operation by attendant.
In sum, a kind of commodity method for quickly identifying based on Image Feature Matching of the present invention and system are by utilizing filming apparatus to take pictures to the commodity to be identified of placing vertically or lying on commodity Transfer pipe, cut apart, extract the color of commodity image, shape low-level feature slightly mates as commodity image, from huge commodity storehouse, screen and remove a large amount of uncorrelated commodity, then utilize surf local invariant feature, carry out exact matching with the commodity characteristics of image in commodity information database after thick coupling, thereby realize commodity identification fast automatically, simultaneously, the present invention carries out numerical coding classification by the CF feature of every kind of commodity, make commodity to be identified directly to the commodity in commodity storehouse, carry out fast search, raising arithmetic speed that can be very large significantly row subtract the commodity amount in commodity storehouse, the commodity storehouse being beneficial to after later use efficient identification algorithm subtracts row is quick and precisely identified.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not for limiting the present invention.Any those skilled in the art all can, under spirit of the present invention and category, modify and change above-described embodiment.Therefore, the scope of the present invention, should be as listed in claims.
Claims (10)
1. the commodity method for quickly identifying based on Image Feature Matching, comprises the steps:
Step 1, utilizes filming apparatus that the commodity to be identified that are positioned on commodity Transfer pipe are taken pictures, cut apart;
Step 2, carries out the extraction of color, shape low-level feature to the commodity image obtaining, and after the color of current commodity to be identified, shape low-level feature are encoded, retrieves and slightly mate, to arrange the commodity that subtract in database in database;
Step 3, utilizes local invariant feature to subtract surplus commodities to row in commodity information database and carries out accurately coupling identification, generates bill.
2. a kind of commodity method for quickly identifying based on Image Feature Matching as claimed in claim 1, it is characterized in that: in step 1, utilize infrared facility to detect after commodity, trigger this filming apparatus, by this filming apparatus, these commodity to be identified are taken pictures, and store in the middle of internal memory.
3. a kind of commodity method for quickly identifying based on Image Feature Matching as claimed in claim 1, is characterized in that, in step 2, color characteristic extraction and the coding of commodity image is comprised the steps:
By image from RGB color space conversion to hsv color space;
Calculate respectively red, orange, yellow, green, cyan, blue, purple, black, white, ten kinds of colors of ash shared color ratio in image;
Setting threshold, quantizes ten kinds of color ratios;
Rear ten kinds of main colors of quantification are divided into some parts, carry out respectively binary coding, and according to coding rule, be commodity distribute digital label, create commodity color coding tables of data.
4. a kind of commodity method for quickly identifying based on Image Feature Matching as claimed in claim 3, it is characterized in that: rear ten kinds of main colors of quantification are divided into 3,3,3,1 four parts, carry out respectively binary coding, be packed data length, to each several part, summation obtains the coded data of four, according to this coding rule simultaneously, for commodity distribute digital label, create commodity color coding tables of data.
5. a kind of commodity method for quickly identifying based on Image Feature Matching as claimed in claim 3, is characterized in that, in step 2, the Shape Feature Extraction of commodity image and coding is comprised the steps:
When the border of object is known, the basic configuration of portraying commodity by the size of its boundary rectangle;
To arbitrarily towards object, first determine the main shaft of object, then calculate length on the major axes orientation of reflection shape feature and the width in perpendicular direction;
Adopt the shape facility that is compared to of horizontal width and vertical width;
Step-up error, by mean value plus-minus 0.3 data that obtain of commodity image length breadth ratio in early stage, coupling take 0.8 as equally spaced data area, and take its region number as its coding, creates commodity coded shape data table.
6. a kind of commodity method for quickly identifying based on Image Feature Matching as claimed in claim 5, is characterized in that: in step 3, be matched to power the highest and be greater than 90% both, think successfully to mate, thereby the merchandise news of obtaining, according to the merchandise news obtaining, generates bill.
7. a kind of commodity method for quickly identifying based on Image Feature Matching as claimed in claim 5, is characterized in that: in step 3, by feature point detection, unique point description and Feature Points Matching, extract this local invariant feature.
8. a kind of commodity method for quickly identifying based on Image Feature Matching as claimed in claim 1, it is characterized in that: in step 2, by server to the color of current commodity to be identified, shape facility according to binary coding after, in database, retrieve and slightly mate.
9. the commodity system for rapidly identifying based on Image Feature Matching, at least comprises:
Image pickup module, utilizes filming apparatus to take the commodity to be identified that are positioned on commodity Transfer pipe;
Characteristic extracting module, carries out the extraction of color, shape low-level feature to the image of current shooting, and the color, the shape facility that extract are encoded, and obtains color coding data and coded shape data;
The thick matching module of feature is retrieved these color coding data and this coded shape data and slightly mates in database, and row subtracts the commodity in database;
SUFT exact matching module, utilizes local invariant feature to subtract surplus commodities to row in database and carries out accurately coupling identification, generates bill.
10. a kind of commodity system for rapidly identifying based on Image Feature Matching as claimed in claim 9, it is characterized in that: this characteristic extracting module utilizes the processing and control module of this filming apparatus to carry out color and Shape Feature Extraction to present image, and by server, it is carried out to binary coding, form color coding data and coded shape data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310637710.0A CN103617420A (en) | 2013-11-27 | 2013-11-27 | Commodity fast recognition method and system based on image feature matching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310637710.0A CN103617420A (en) | 2013-11-27 | 2013-11-27 | Commodity fast recognition method and system based on image feature matching |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103617420A true CN103617420A (en) | 2014-03-05 |
Family
ID=50168123
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310637710.0A Pending CN103617420A (en) | 2013-11-27 | 2013-11-27 | Commodity fast recognition method and system based on image feature matching |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103617420A (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105157742A (en) * | 2014-04-29 | 2015-12-16 | 杭州美盛红外光电技术有限公司 | Identification device and identification method |
CN105224913A (en) * | 2015-09-01 | 2016-01-06 | 上海斐讯数据通信技术有限公司 | A kind of number of articles detection method and device |
CN105488509A (en) * | 2015-11-19 | 2016-04-13 | Tcl集团股份有限公司 | Image clustering method and system based on local chromatic features |
CN105868772A (en) * | 2016-03-23 | 2016-08-17 | 百度在线网络技术(北京)有限公司 | Image identification method and apparatus |
CN105921886A (en) * | 2016-06-29 | 2016-09-07 | 韦醒妃 | High-recognition-performance laser processing machine tool |
CN105959561A (en) * | 2016-06-13 | 2016-09-21 | Tcl集团股份有限公司 | Photographing method and system |
CN106077971A (en) * | 2016-06-29 | 2016-11-09 | 韦醒妃 | A kind of can the laser cutting device of autonomous classification |
WO2017012277A1 (en) * | 2015-07-22 | 2017-01-26 | 杭州海康威视数字技术股份有限公司 | Method and device for searching a target in an image |
CN106485196A (en) * | 2015-08-28 | 2017-03-08 | 意法半导体股份有限公司 | Visual search method, corresponding system, equipment and computer program |
CN107169425A (en) * | 2017-04-26 | 2017-09-15 | 深圳美云智数科技有限公司 | A kind of recognition methods of item property and device |
CN107292248A (en) * | 2017-06-05 | 2017-10-24 | 广州诚予国际市场信息研究有限公司 | A kind of merchandise control method and system based on image recognition technology |
CN107610381A (en) * | 2017-10-19 | 2018-01-19 | 安徽小豆网络科技有限公司 | A kind of self-service cashier's machine of view-based access control model image recognition |
CN107730782A (en) * | 2017-10-19 | 2018-02-23 | 安徽小豆网络科技有限公司 | Unmanned convenience store's operation system of the self-service cashier's machine of view-based access control model image recognition |
CN107767590A (en) * | 2016-08-16 | 2018-03-06 | 深圳仪普生科技有限公司 | Automatic identification commercialization bar code electronic scale and Automatic identification method |
CN107862814A (en) * | 2017-11-01 | 2018-03-30 | 北京旷视科技有限公司 | Automated Clearing House system and automatic settlement method |
CN108171846A (en) * | 2017-12-30 | 2018-06-15 | 南京陶特思软件科技有限公司 | There is the access control system of fast verification |
CN108345912A (en) * | 2018-04-25 | 2018-07-31 | 电子科技大学中山学院 | Commodity rapid settlement system based on RGBD information and deep learning |
CN108364420A (en) * | 2018-01-08 | 2018-08-03 | 阿里巴巴集团控股有限公司 | Image-recognizing method and device and electronic equipment |
CN109543057A (en) * | 2018-11-20 | 2019-03-29 | 广州逗号智能零售有限公司 | Commodity recognition method, device, equipment and storage medium based on intelligent cashier platform |
CN109741551A (en) * | 2018-12-24 | 2019-05-10 | 青岛海信智能商用系统股份有限公司 | A kind of commodity identification settlement method, apparatus and system |
CN110414645A (en) * | 2018-04-28 | 2019-11-05 | 深圳果力智能科技有限公司 | A kind of pattern recognition method based on Match of elemental composition |
CN110490211A (en) * | 2019-08-23 | 2019-11-22 | 郑州航空工业管理学院 | A kind of button identification method based on feature extraction |
CN111126384A (en) * | 2019-12-12 | 2020-05-08 | 创新奇智(青岛)科技有限公司 | Commodity classification system and method based on feature fusion |
CN111967942A (en) * | 2020-08-20 | 2020-11-20 | 渭南双盈未来科技有限公司 | Intelligent shopping method |
CN112272838A (en) * | 2018-06-07 | 2021-01-26 | 株式会社资生堂 | Commodity specifying device, program, and learning method |
CN115965797A (en) * | 2022-12-27 | 2023-04-14 | 北京国电光宇机电设备有限公司 | Automatic identification method and system for intelligent assembly parts |
CN116721411A (en) * | 2023-02-09 | 2023-09-08 | 浙江由由科技有限公司 | Bulk snack identification method based on machine learning |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101655960A (en) * | 2008-08-20 | 2010-02-24 | 索尼株式会社 | Commodity marketing system |
CN102063436A (en) * | 2009-11-18 | 2011-05-18 | 腾讯科技(深圳)有限公司 | System and method for realizing merchandise information searching by using terminal to acquire images |
CN102063616A (en) * | 2010-12-30 | 2011-05-18 | 上海电机学院 | Automatic identification system and method for commodities based on image feature matching |
CN102298779A (en) * | 2011-08-16 | 2011-12-28 | 淮安盈科伟力科技有限公司 | Image registering method for panoramic assisted parking system |
-
2013
- 2013-11-27 CN CN201310637710.0A patent/CN103617420A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101655960A (en) * | 2008-08-20 | 2010-02-24 | 索尼株式会社 | Commodity marketing system |
CN102063436A (en) * | 2009-11-18 | 2011-05-18 | 腾讯科技(深圳)有限公司 | System and method for realizing merchandise information searching by using terminal to acquire images |
CN102063616A (en) * | 2010-12-30 | 2011-05-18 | 上海电机学院 | Automatic identification system and method for commodities based on image feature matching |
CN102298779A (en) * | 2011-08-16 | 2011-12-28 | 淮安盈科伟力科技有限公司 | Image registering method for panoramic assisted parking system |
Cited By (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105157742B (en) * | 2014-04-29 | 2021-03-23 | 杭州美盛红外光电技术有限公司 | Identification device and identification method |
CN105157742A (en) * | 2014-04-29 | 2015-12-16 | 杭州美盛红外光电技术有限公司 | Identification device and identification method |
WO2017012277A1 (en) * | 2015-07-22 | 2017-01-26 | 杭州海康威视数字技术股份有限公司 | Method and device for searching a target in an image |
EP3327583A4 (en) * | 2015-07-22 | 2019-02-06 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and device for searching a target in an image |
US10678847B2 (en) | 2015-07-22 | 2020-06-09 | Hangzhou Hikvision Digital Technology Co., Ltd. | Method and device for searching a target in an image |
CN106485196A (en) * | 2015-08-28 | 2017-03-08 | 意法半导体股份有限公司 | Visual search method, corresponding system, equipment and computer program |
US10585937B2 (en) | 2015-08-28 | 2020-03-10 | Stmicroelectronics S.R.L. | Method for visual search, corresponding system, apparatus and computer program product |
CN105224913A (en) * | 2015-09-01 | 2016-01-06 | 上海斐讯数据通信技术有限公司 | A kind of number of articles detection method and device |
CN105488509A (en) * | 2015-11-19 | 2016-04-13 | Tcl集团股份有限公司 | Image clustering method and system based on local chromatic features |
CN105868772A (en) * | 2016-03-23 | 2016-08-17 | 百度在线网络技术(北京)有限公司 | Image identification method and apparatus |
US10706314B2 (en) | 2016-03-23 | 2020-07-07 | Baidu Online Network Technology (Beijing) Co., Ltd. | Image recognition method, apparatus and device, and non-volatile computer storage medium |
CN105959561A (en) * | 2016-06-13 | 2016-09-21 | Tcl集团股份有限公司 | Photographing method and system |
CN106077971A (en) * | 2016-06-29 | 2016-11-09 | 韦醒妃 | A kind of can the laser cutting device of autonomous classification |
CN105921886B (en) * | 2016-06-29 | 2018-06-26 | 江苏大金激光科技有限公司 | A kind of laser process machine of high recognition performance |
CN105921886A (en) * | 2016-06-29 | 2016-09-07 | 韦醒妃 | High-recognition-performance laser processing machine tool |
CN106077971B (en) * | 2016-06-29 | 2018-03-20 | 中江机电科技江苏有限公司 | A kind of laser cutting device for being capable of autonomous classification |
CN107767590A (en) * | 2016-08-16 | 2018-03-06 | 深圳仪普生科技有限公司 | Automatic identification commercialization bar code electronic scale and Automatic identification method |
CN107169425A (en) * | 2017-04-26 | 2017-09-15 | 深圳美云智数科技有限公司 | A kind of recognition methods of item property and device |
CN107292248A (en) * | 2017-06-05 | 2017-10-24 | 广州诚予国际市场信息研究有限公司 | A kind of merchandise control method and system based on image recognition technology |
CN107292248B (en) * | 2017-06-05 | 2023-04-07 | 广州诚予国际市场信息研究有限公司 | Commodity management method and system based on image recognition technology |
CN107610381A (en) * | 2017-10-19 | 2018-01-19 | 安徽小豆网络科技有限公司 | A kind of self-service cashier's machine of view-based access control model image recognition |
CN107730782A (en) * | 2017-10-19 | 2018-02-23 | 安徽小豆网络科技有限公司 | Unmanned convenience store's operation system of the self-service cashier's machine of view-based access control model image recognition |
CN107862814A (en) * | 2017-11-01 | 2018-03-30 | 北京旷视科技有限公司 | Automated Clearing House system and automatic settlement method |
CN108171846A (en) * | 2017-12-30 | 2018-06-15 | 南京陶特思软件科技有限公司 | There is the access control system of fast verification |
CN108364420A (en) * | 2018-01-08 | 2018-08-03 | 阿里巴巴集团控股有限公司 | Image-recognizing method and device and electronic equipment |
CN108345912A (en) * | 2018-04-25 | 2018-07-31 | 电子科技大学中山学院 | Commodity rapid settlement system based on RGBD information and deep learning |
CN110414645B (en) * | 2018-04-28 | 2023-05-30 | 深圳果力智能科技有限公司 | Pattern recognition method based on element matching |
CN110414645A (en) * | 2018-04-28 | 2019-11-05 | 深圳果力智能科技有限公司 | A kind of pattern recognition method based on Match of elemental composition |
CN112272838A (en) * | 2018-06-07 | 2021-01-26 | 株式会社资生堂 | Commodity specifying device, program, and learning method |
CN109543057A (en) * | 2018-11-20 | 2019-03-29 | 广州逗号智能零售有限公司 | Commodity recognition method, device, equipment and storage medium based on intelligent cashier platform |
CN109741551A (en) * | 2018-12-24 | 2019-05-10 | 青岛海信智能商用系统股份有限公司 | A kind of commodity identification settlement method, apparatus and system |
CN109741551B (en) * | 2018-12-24 | 2021-09-24 | 青岛海信智能商用系统股份有限公司 | Commodity identification settlement method, device and system |
CN110490211A (en) * | 2019-08-23 | 2019-11-22 | 郑州航空工业管理学院 | A kind of button identification method based on feature extraction |
CN111126384A (en) * | 2019-12-12 | 2020-05-08 | 创新奇智(青岛)科技有限公司 | Commodity classification system and method based on feature fusion |
CN111967942A (en) * | 2020-08-20 | 2020-11-20 | 渭南双盈未来科技有限公司 | Intelligent shopping method |
CN115965797A (en) * | 2022-12-27 | 2023-04-14 | 北京国电光宇机电设备有限公司 | Automatic identification method and system for intelligent assembly parts |
CN115965797B (en) * | 2022-12-27 | 2023-12-08 | 北京国电光宇机电设备有限公司 | Automatic identification method and system for intelligent assembly parts |
CN116721411A (en) * | 2023-02-09 | 2023-09-08 | 浙江由由科技有限公司 | Bulk snack identification method based on machine learning |
CN116721411B (en) * | 2023-02-09 | 2024-06-04 | 浙江由由科技有限公司 | Bulk snack identification method based on machine learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103617420A (en) | Commodity fast recognition method and system based on image feature matching | |
Gan et al. | Immature green citrus fruit detection using color and thermal images | |
US10127688B2 (en) | System and process for automatically finding objects of a specific color | |
WO2018095142A1 (en) | Livestream interaction method and apparatus | |
Liu et al. | A smart unstaffed retail shop based on artificial intelligence and IoT | |
CN108734185B (en) | Image verification method and device | |
CN104021207B (en) | A kind of food information providing method based on image | |
CN110348439B (en) | Method, computer readable medium and system for automatically identifying price tags | |
Ren et al. | General traffic sign recognition by feature matching | |
WO2016004330A1 (en) | Interactive content generation | |
Marder et al. | Using image analytics to monitor retail store shelves | |
CN109116129B (en) | Terminal detection method, detection device, system and storage medium | |
CN113627411A (en) | Super-resolution-based commodity identification and price matching method and system | |
CN112149690A (en) | Tracing method and tracing system based on biological image feature recognition | |
CN113469216B (en) | Retail terminal poster identification and integrity judgment method, system and storage medium | |
CN111428743B (en) | Commodity identification method, commodity processing device and electronic equipment | |
CN110705620A (en) | Display image detection method and device based on copying recognition and storage medium | |
CN110569716A (en) | Goods shelf image copying detection method | |
Martinel et al. | Robust painting recognition and registration for mobile augmented reality | |
CN110969454A (en) | Cosmetics propaganda and promotion system based on intelligent product album | |
CN115661624A (en) | Digital method and device for goods shelf and electronic equipment | |
CN111461104B (en) | Visual recognition method, device, equipment and storage medium | |
CN104867026B (en) | Method and system for providing commodity image and terminal device for outputting commodity image | |
CN113379669A (en) | Method, device and equipment for beverage cabinet image recognition | |
CN109597905A (en) | A kind of data-acquisition system and method applied to artistic work |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140305 |
|
RJ01 | Rejection of invention patent application after publication |